Organize work by task, track tokens/cost per task, and keep a small patchable execution state that is re-injected after /compact (SKILL.state-style) — start a task, patch its state, list tasks, or…

MITAuto-check passed

Install Cco Task

skills CLI
$ npx skills add egorfedorov/claude-context-optimizer --skill cco-task -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install egorfedorov/claude-context-optimizer cco-task --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/egorfedorov/claude-context-optimizer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cco-task .claude/skills/cco-task && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
cco-task
GitHub stars
114
Token cost
~866 tokens
SKILL.md length
409 words
Files
1
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

Organize work by task, track tokens/cost per task, and keep a small patchable execution state that is re-injected after /compact (SKILL.state-style) — start a task, patch its state, list tasks, or…

  • Works in 5 steps: /cco-task add "implement X" — start the… → /cco-pack "implement X" — load only the… → /cco-task patch '{"goal": "...", "next":… → …
  • SKILL.md covers Commands, State discipline (what makes… and Flow to recommend
  • Calls node

What it does

Cco Task is an agent skill from egorfedorov/claude-context-optimizer. Organize work by task, track tokens/cost per task, and keep a small patchable execution state that is re-injected after /compact (SKILL.state-style) — start a task, patch its state, list tasks, or mark the active one done. Pairs with /cco-pack to load minimal context per task.

Its SKILL.md is about 870 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Claude Code plugin that tracks token usage, identifies wasted context, and saves 30-50% on API costs. Heatmaps, ROI reports, budget alerts, efficiency scores, git-aware… The licence is MIT.

Example prompts

  • “/cco-task”

Requirements

  • Pre-approved tools (allowed-tools): Bash(node ${CLAUDE_PLUGIN_ROOT}/src/tasks.js:*)

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. /cco-task add "implement X" — start the task
  2. /cco-pack "implement X" — load only the files that task needs
  3. /cco-task patch '{"goal": "...", "next": "..."}' — seed the state; patch as you go
  4. /cco — see budget, savings, and this task's cost
  5. /cco-task done — freeze the task's token/$ total

What it can do on your machine

Read from SKILL.md and the folder at commit f6f20ee. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(node ${CLAUDE_PLUGIN_ROOT}/src/tasks.js:*)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cco Task loads about 866 tokens when it runs. Until then it costs about 72 tokens; SKILL.md has 409 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~72
When it runs · the whole SKILL.md, loaded when a task matches
~866

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from egorfedorov/claude-context-optimizer at commit f6f20ee, republished under its MIT licence (© egorfedorov). 409 words, ~866 tokens.

Download SKILL.mdSave it as .claude/skills/cco-task/SKILL.md (or your agent's skills folder).
name
cco-task
description
Organize work by task, track tokens/cost per task, and keep a small patchable execution state that is re-injected after /compact (SKILL.state-style) — start a task, patch its state, list tasks, or mark the active one done. Pairs with /cco-pack to load minimal context per task.
allowed-tools
Bash(node ${CLAUDE_PLUGIN_ROOT}/src/tasks.js:*)
license
MIT
argument-hint
[add "<name>" | patch '<json>' | state | list | done [note]]

Tasks — per-task context, cost, and execution state

A task is a named unit of work. While a task is active, the tokens the session spends are attributed to it, so the Control Center (/cco) can show cost per task, not just per session.

Each task also carries a small JSON execution state — goal, what is done, what is open, the next action. You update it with patches instead of re-deriving progress from the transcript, it is capped at ~1K tokens so it never grows with the number of steps, and it is re-injected verbatim right after /compact (and on --resume). That is the SKILL.state idea (Google / Purdue, 2026) applied where a plugin can apply it: the compaction summary is lossy and free-form; the state is exact and bounded.

Commands

Parse the user's argument and run the matching command (working directory scopes the tasks to the current project):

Start / switch task (also closes the previous active task):

bash
node ${CLAUDE_PLUGIN_ROOT}/src/tasks.js add "<task name>"

After starting, suggest packing the minimal context for it: /cco-pack "<task name>", and seed the state with the goal and the plan: /cco-task patch '{"goal": "...", "plan": ["...", "..."], "next": "..."}'.

Patch the execution state (set keys; null deletes a key):

bash
node ${CLAUDE_PLUGIN_ROOT}/src/tasks.js patch '{"done": ["read auth.ts"], "next": "write the failing test", "scratch": null}'

The patch must be a JSON object. If the state would exceed the cap the patch is rejected — prune finished keys with null first.

Show the current state:

bash
node ${CLAUDE_PLUGIN_ROOT}/src/tasks.js state

List tasks (newest first, with per-task tokens + $):

bash
node ${CLAUDE_PLUGIN_ROOT}/src/tasks.js list

Complete the active task:

bash
node ${CLAUDE_PLUGIN_ROOT}/src/tasks.js done
Show full SKILL.md (177 more words)Show less

State discipline (what makes it worth keeping)

  • Keep it a state, not a log: done, open, next, decisions, files — facts needed to continue, not the history of how you got there. Reasoning is ephemeral; the state is what survives.
  • Patch after each milestone (a test passing, a decision made, a file finished), and delete keys the moment they stop mattering.
  • After /compact the SessionStart hook prints the active task's state into the new context automatically — treat it as authoritative over the summary.
  • When delegating to a subagent, pass the state (not the conversation) as the brief; it is already the minimal, current description of the task.

Flow to recommend

  1. /cco-task add "implement X" — start the task
  2. /cco-pack "implement X" — load only the files that task needs
  3. /cco-task patch '{"goal": "...", "next": "..."}' — seed the state; patch as you go
  4. /cco — see budget, savings, and this task's cost
  5. /cco-task done — freeze the task's token/$ total

Only one task is active per project at a time; starting a new one finalizes the previous task's cost automatically.

© egorfedorov, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/cco-task of egorfedorov/claude-context-optimizer.

Open the folder on GitHubat commit f6f20ee

Compare with similar skills

Cco Task next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Cco Task compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cco Task this skillegorfedorov/claude-context-optimizer114—~866Automated safety check: PassMIT
Cost Trackingaffaan-m/ECC276k1 repos~1.3kAutomated safety check: PassMIT
Cost Conversationruvnet/ruflo74k—~407Automated safety check: NotesMIT
Cost Reportruvnet/ruflo74k—~830Automated safety check: NotesMIT
Cost Optimizeruvnet/ruflo74k—~997Automated safety check: NotesMIT
Cost Trackruvnet/ruflo74k—~773Automated safety check: NotesMIT

Similar skills

  • Cost Tracking

    affaan-m/ECC

    Track and report Claude Code token usage, spending, and budgets from the local ECC cost-tracker metrics log.

    276k GitHub starsUsed in 1 repo~1.3k tokens
    AI & LLM EngineeringAuto-check passed
  • Cost Conversation

    ruvnet/ruflo

    Per-conversation cost view — list every session in cost-tracking with started-at, message count, top model, and total cost

    74k GitHub stars~407 tokensUpdated today
    AI & LLM EngineeringAuto-check: notes
  • Cost Report

    ruvnet/ruflo

    Generate a cost report showing token usage and USD costs by agent and model

    74k GitHub stars~830 tokensUpdated today
    AI & LLM EngineeringAuto-check: notes
  • Cost Optimize

    ruvnet/ruflo

    Analyze token usage patterns and recommend cost optimizations with estimated savings

    74k GitHub stars~997 tokensUpdated today
    AI & LLM EngineeringAuto-check: notes
  • Cost Track

    ruvnet/ruflo

    Auto-capture per-session token usage from the Claude Code session jsonl and persist to the cost-tracking namespace

    74k GitHub stars~773 tokensUpdated today
    AI & LLM EngineeringAuto-check: notes
  • Cost Export

    ruvnet/ruflo

    Export cost-tracking telemetry in Prometheus textfile or webhook JSON formats — for external observability (Grafana, Datadog, custom dashboards)

    74k GitHub stars~687 tokensUpdated today
    DevOps & CloudAuto-check: notes

More from egorfedorov/claude-context-optimizer

All 13 skills in this repo
  • Smart Loader

    egorfedorov/claude-context-optimizer

    Automatically suggests optimal files to preload based on the user's task description and historical context patterns.

    114 GitHub stars~530 tokensUpdated 9 days ago
    Auto-check passed
  • Cco

    egorfedorov/claude-context-optimizer

    Context Control Center — one screen for budget, $ spent, tokens saved, waste, last prompt grade, the active task, and ready-to-run optimization actions

    114 GitHub stars~465 tokensUpdated 9 days ago
    Auto-check passed
  • Cco Budget

    egorfedorov/claude-context-optimizer

    Configure token budget limits, auto-compact settings, and view current budget status (model-aware — Claude 5 lineup, Opus 5.5 default fallback, full 1M context at standard price)

    114 GitHub stars~808 tokensUpdated 9 days ago
    Auto-check passed
  • Cco Config

    egorfedorov/claude-context-optimizer

    View and tune CCO's behavior thresholds — re-read warnings, cache staleness, prompt-coach length bands, and the /cco-pack budget cap

    114 GitHub stars~839 tokensUpdated 9 days ago
    Auto-check passed
  • Cco Patterns

    egorfedorov/claude-context-optimizer

    Share learned file patterns across a team — export an anonymized digest of what's usually waste/useful/co-edited, and import a teammate's so a fresh clone benefits day one

    114 GitHub stars~665 tokensUpdated 9 days ago
    Auto-check passed
  • Cco Shield

    egorfedorov/claude-context-optimizer

    Show ContextShield status and waste protection stats; suggest or apply .contextignore rules from historical waste

    114 GitHub stars~457 tokensUpdated 9 days ago
    Auto-check passed

Questions about Cco Task

What does Cco Task do?

Organize work by task, track tokens/cost per task, and keep a small patchable execution state that is re-injected after /compact (SKILL.state-style) — start a task, patch its state, list tasks, or…. Cco Task is an agent skill from egorfedorov/claude-context-optimizer.state-style) — start a task, patch its state, list tasks, or mark the active one done.

How do I install Cco Task in Claude Code?

Run `npx skills add egorfedorov/claude-context-optimizer --skill cco-task -a claude-code`. Or copy the skill folder (skills/cco-task in egorfedorov/claude-context-optimizer) into .claude/skills/cco-task in your project. Claude Code loads it when a task matches its description.

How do I install Cco Task in Codex?

Run `npx skills add egorfedorov/claude-context-optimizer --skill cco-task -a codex`. Or copy the skill folder (skills/cco-task in egorfedorov/claude-context-optimizer) into .agents/skills/cco-task in your project. Codex loads it when a task matches its description.

Can I use Cco Task in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add egorfedorov/claude-context-optimizer --skill cco-task -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cco-task, .gemini/skills/cco-task, .github/skills/cco-task and .opencode/skills/cco-task in your project.

What does Cco Task need to run?

Going by SKILL.md and its folder, Cco Task needs the command-line tools its instructions call (node). Its frontmatter pre-approves these tools: Bash(node ${CLAUDE_PLUGIN_ROOT}/src/tasks.js:*).

Does Cco Task access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Cco Task safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Cco Task use?

Cco Task is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cco Task use?

About 866 tokens (SKILL.md is roughly 3.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Cco Task?

Skills that share tags, products or a category with Cco Task: Cost Tracking (affaan-m/ECC, 276k stars), Cost Conversation (ruvnet/ruflo, 74k stars), Cost Report (ruvnet/ruflo, 74k stars) and Cost Optimize (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cco Task?

egorfedorov (a GitHub user) maintains it in egorfedorov/claude-context-optimizer, which has 114 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on September 30, 2026.

Source: egorfedorov/claude-context-optimizer on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.